NYU Grossman School of Medicine is a leader among medical schools in the use of sophisticated tools to collect, analyze, and display electronic-learning data. The opportunities presented by such data have the potential to be transformative: our evaluation of the effectiveness of curricula can move from the anecdotal to the epidemiologic; detailed learner-level data can drive the move toward individualized learning and personalized progression; and the analysis of changes in performance over time can propel us toward health education that is competency driven.

Education Data Warehouse

The Institute for Innovations in Medical Education pioneered the development of an integrated system and central repository for its education data called the Education Data Warehouse. Coupled with advanced analytical tools and business intelligence software, the Education Data Warehouse allows us to manage, visualize, and learn from large educational data sets and establish performance goals for NYU Grossman School of Medicine’s academic mission.

Our Division of Education Quality and Division of Academic Analytics guide the medical school’s transformation to a data-driven culture by delivering high-quality longitudinal education data to leaders, faculty, and learners in order to generate knowledge and insight. Oversight and stewardship related to the protection of, access to, and best use of electronic learning and outcomes data from NYU Grossman School of Medicine students, house staff, and faculty are provided by the Education Data for Innovations Committee. Membership includes a student ombudsman and representatives from the Institute for Innovations in Medical Education and the following areas:

• Education, Faculty, and Academic Affairs
• Faculty Council
• Medical Center Information Technology (MCIT)
• Office of Diversity Affairs
• Office of Graduate Medical Education
• Office of Medical Education
• Office of Registration and Student Records
• Office of Student Affairs

Our partners include the Institute for Computational Medicine, Center for Early Childhood Health and Development, Predictive Analytics Unit, and Enterprise Data Warehousing and Analytics.

Our quality improvement and innovation projects are described below. Please email edu.data@nyulangone.org if you have any questions.

Dashboards That Transform Education

Because of the increasing reliance on data to make decisions, we seek to empower end-users with more self-service business intelligence tools. This approach allows NYU Grossman School of Medicine to reallocate technical resources to enhance its dashboards with advanced algorithms, natural language processing, and machine learning for forecasting. We partner closely with many stakeholders, including administrators, educators, and members of the MCIT team, to ensure the success of this initiative.

Tracer Project

The Tracer Project focuses on using publicly available practice data to better understand the influences of education programs on quality outcome measures. By doing so, we are able to evaluate several issues both on the school and national levels, such as the relationship between curricular reform and the ultimate outcomes, value, and quality of care delivered; a deeper understanding of which patients our graduates are caring for and in what settings; and predictive models of what care will look like and what skills will be needed by current students and trainees.

Data that is in the public domain can also facilitate groups of schools, organized either geographically or around a common purpose, to collaborate on national research questions. Secondary uses of these data by medical education researchers could also include retrospective and prospective analysis to validate prior medical education studies.

Natural Language Processing and Machine Learning

NYU Grossman School of Medicine uses natural language processing and machine learning to drive predictive analytics for the improvement and optimization of teaching and learning. Examples include the following:

• identifying hidden patterns and relationships among variables in student performance and behavior for personalization and early intervention
• automating, improving, and accelerating manual evaluations and assessments
• providing immediate feedback to students and faculty
• summarizing volumes of textual data in a comprehensive and concise way to facilitate decision making